Visual Gesture Recognition via Motion-Assisted Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing human computer interface solutions face challenges such as limited platform size, computing power, and bandwidth, making them complex and inefficient for recognizing human visual gestures, particularly in applications like hand gesture recognition.
Innovation Solution
A computer-implemented method using shape-based, position-based, and motion-assisted gesture recognition processes, combined with dual object tracking, to recognize human visual gestures captured by image and video sensors, enabling efficient and robust visual language development for various human computer interfaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple sensors including specialized infrared depth sensors are used for gesture recognition, then gesture recognition accuracy is improved, but device complexity increases
Solution Approach 1:
The patent extracts and removes the specialized infrared depth sensor from the system, relying instead on standard image/video cameras to capture gestures. This eliminates the need for complex specialized hardware while maintaining gesture recognition functionality through software-based processing of visual data from conventional sensors.
Solution Approach 2:
The patent makes standard image and video sensors perform the gesture recognition function previously requiring specialized depth sensors. By using multi-functional conventional cameras for both general imaging and gesture capture, the system avoids the complexity of dedicated specialized sensors while achieving the same recognition goals.
2Ease of operation
If traditional keyboards and mice are replaced with touch screens and gesture recognition, then user convenience is improved, but interface complexity increases
Solution Approach 1:
The system uses the device's existing camera hardware to automatically capture and process gestures without requiring additional specialized sensors. The conventional image sensors serve dual purposes (general imaging and gesture recognition), allowing the system to provide enhanced user interaction capabilities while avoiding the complexity of dedicated gesture capture hardware.
3Measurement precision
If gesture recognition processes are applied to multiple video frames, then recognition accuracy is improved, but computing power requirements increase
Solution Approach 1:
The patent processes video frames in a segmented manner, analyzing gestures across multiple frames through systematic breakdown of the recognition process into discrete steps (detecting visual contours, applying parametric models, tracking motion). This segmentation allows efficient processing that maintains accuracy while optimizing computational resource usage.
Data Source
AI summary
Embodiments of the invention recognize human visual gestures, as captured by image and video sensors, to develop a visual language for a variety of human computer interfaces. One embodiment of the invention provides a computer-implement method for recognizing a visual gesture portrayed by a part of human body such as a human hand, face or body. The method includes steps of receiving the visual signature captured in a video having multiple video frames, determining a gesture recognition type from multiple gesture recognition types including shaped-based gesture, position-based gesture, motion-assisted and mixed gesture that combining two different gesture types. The method further includes steps of selecting a visual gesture recognition process based on the determined gesture type and applying the selected visual gesture recognition process to the multiple video frames capturing the visual gesture to recognize the visual gesture.